Repolode
Submit
chidiwilliams

chidiwilliams/buzz

Desktop app that transcribes and translates audio and video offline on your computer, built on OpenAI's Whisper.

Open-source alternative to:Otter.aiDescript

View on GitHubWebsite
Stars
22,078
Forks
1,632
Open issues
21
Last commit
3 days ago

What is it?

Buzz is a desktop application for transcribing and translating audio offline on your own computer. It wraps OpenAI's Whisper speech recognition models in a graphical interface, so you can process local files, YouTube links, or live microphone input without sending audio to a cloud service.

Beyond basic transcription, Buzz offers speaker identification, speech separation for noisy recordings, and a transcript viewer with search and playback controls. Transcripts can be exported to TXT, SRT, and VTT. It supports several Whisper backends, including GPU acceleration on Nvidia CUDA, Apple Silicon, and Vulkan for a range of GPUs.

Buzz is available for macOS, Windows, and Linux through installers, Flatpak, Snap, and PyPI. A command-line interface and a watch folder mode support scripting and automated workflows.

Key features

  • 01Transcribes audio and video files as well as YouTube links
  • 02Live transcription from microphone with a presentation window
  • 03Speaker identification and speech separation for noisy audio
  • 04Exports transcripts to TXT, SRT, and VTT
  • 05Supports CUDA, Apple Silicon, and Vulkan acceleration
  • 06Command-line interface and watch folder for automation

Use cases

  • Creating subtitles for local videos without uploading them to a cloud service
  • Generating live captions for presentations and events
  • Transcribing interviews or meetings with speaker labels
  • Batch processing new recordings through a watch folder

Quick start

  1. 1

    Download the .dmg, .exe or installer from SourceForge, or install from Flathub/Snap

  2. 2

    Install Flatpak version via Flathub

    flatpak install flathub io.github.chidiwilliams.Buzz
  3. 3

    Install ffmpeg, then install Buzz from PyPI (Python 3.12)

    pip install buzz-captions
  4. 4

    Run Buzz from the command line

    python -m buzz

Things to know

  • Intel Macs are no longer supported; the last compatible version is 1.4.5.
  • Windows builds are unsigned, so installers show a warning.
  • GPU acceleration for Nvidia on PyPI installs requires extra CUDA-specific torch packages.

Topics

#whisper#speech-to-text#transcription#translation#offline#subtitles#desktop-app

FAQ

What is buzz?
Desktop app that transcribes and translates audio and video offline on your computer, built on OpenAI's Whisper. Buzz is a desktop application for transcribing and translating audio offline on your own computer. It wraps OpenAI's Whisper speech recognition models in a graphical interface, so you can process local files, YouTube links, or live microphone input without sending audio to a cloud service.
Is buzz free to use? What license does it have?
buzz is open source under the MIT license. Check the license terms before using it in commercial products.
Is buzz still maintained?
Actively maintained. The last commit to buzz was on Oct 17, 2026.
What can I use buzz for?
Creating subtitles for local videos without uploading them to a cloud service Generating live captions for presentations and events Transcribing interviews or meetings with speaker labels Batch processing new recordings through a watch folder
How do I install buzz?
Download the .dmg, .exe or installer from SourceForge, or install from Flathub/Snap Install Flatpak version via Flathub: flatpak install flathub io.github.chidiwilliams.Buzz Install ffmpeg, then install Buzz from PyPI (Python 3.12): pip install buzz-captions Run Buzz from the command line: python -m buzz
Where can I get buzz?
The source code and installation instructions are on GitHub: https://github.com/chidiwilliams/buzz

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects